Update app.py

app.py

@@ -12,13 +12,12 @@ max_new_tokens = 1096,
 threads = 3,
 )
 
-def stream(user_prompt, mok):
+def stream(prompt, **kwargs):
     system_prompt = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.'
     E_INST = "</s>"
     user, assistant = "<|user|>", "<|assistant|>"
-    prompt = f"{system_prompt}{E_INST}\n{user}\n{user_prompt.strip()}{E_INST}\n{assistant}\n"
-    for text in llm(prompt, stream=True, threads=3):
-        print(text, end="", flush=True)
+    prompt = f"{system_prompt}{E_INST}\n{user}\n{item.prompt.strip()}{E_INST}\n{assistant}\n"
+    return llm(prompt)
 
 css = """
   h1 {
@@ -39,7 +38,7 @@ css = """
 
 chat_interface = gr.ChatInterface(
     fn=stream,
-    additional_inputs_accordion_name = "Credentials",
+    #additional_inputs_accordion_name = "Credentials",
     #additional_inputs=[
     #     gr.Textbox(label="OpenAI Key", lines=1),
     #     gr.Textbox(label="Linkedin Access Token", lines=1),